Explore the vast range of titles available.

Simulation‐optimization methods are commonly used in groundwater pollution source identification. Traditional simulation‐optimization methods require multiple calls to the numerical model, which leads to a considerable computational burden. Surrogate models based on machine learning can replace numerical models while maintaining accuracy. Previous studies have focused on the fitting accuracy of surrogate models, this study emphasizes the importance of the precision of surrogate models for the inversion process. We use the analytic hierarchy process to integrate ConvLSTM, convolutional neural network, and BiLSTM to improve the precision of the surrogate model. GMS is used to construct numerical models of two hypothetical cases and a practical case. Compared with the best results of the single deep learning methods, the integrated surrogate model improves the precision of the solution of the two hypothetical cases by 90% and 26%, respectively. In addition, the accuracy of the pollution source information obtained by incorporating the integrated surrogate model into the optimization model is higher than that obtained by ConvLSTM as the surrogate model. The inversion results of 7 metaheuristic optimization algorithms are compared through two hypothetical cases, and then the optimization algorithm with higher accuracy is applied to the solution of the practical case. To obtain more accurate results, we reobtain a batch of training data by resampling and training the integrated surrogate model. The results show that constructing an integrated surrogate model and selecting an optimization algorithm can improve the solution accuracy of the simulation‐optimization method. This research provides a new perspective for the construction of simulation‐optimization methods.

There are several methods available for modeling sustainable supply chain and logistics (SSCL) issues. Multi-objective optimization (MOO) has been a widely used method in SSCL modeling (SSCLM), nonetheless selecting a suitable optimization technique and solution method is still of interest as model performance is highly dependent on decision-making variables of the model development process. This study provides insights from the analysis of 95 scholarly articles to identify research gaps in the MOO for SSCLM and to assist decision-makers in selecting suitable MOO techniques and solution methods. The results of the analysis indicate that economic and environmental aspects of sustainability are the main context of SSCLM, where the social aspect is still limited. More SSCLMs for sourcing, distribution, and transportation phases of the supply chain are required. Additionally, more sophisticated techniques and solution methods, including hybrid metaheuristics approaches, are needed in SSCLM.

This paper presents an adaptive multi-tracker optimization algorithm (AMTOA) for global optimization problems with an emphasis on applications in chemical engineering. To obtain the AMTOA, first, several modifications are performed on the conventional multi-tracker optimization algorithm (MTOA). Then a number of its parameters are considered to be adaptive. The modifications include a novel way of determining the search radius of each global tracker (GT), and introducing a more efficacious technique of searching for a new solution by GTs. GTs are the main components of the MTOA which look for the global optimal point (GOP). Additionally, the adaptation rules are employed for GTs search radii and their searching parameters. These modifications lead to increasing the precision of the solution and reliability of the algorithm, both of which are the most important properties of an optimizer. Reducing the number of parameters of MTOA is another advantage of AMTOA. The results of applying this algorithm to several unconstrained and constrained general benchmarks along with several chemical engineering optimization problems reveal that AMTOA outperforms other well-known methods such as genetic algorithm (GA), particle swarm optimization (PSO), gray wolf optimizer (GWO), whale optimization algorithm (WOA), and conventional MTOA. Additionally, comparing the results of AMTOA to other advanced optimization algorithms such as LSHADE44, MA-ES, and IUDE show its superiority for chemical engineering optimization problems. Thus, the development of AMTOA could be advantageous to the area of chemical engineering.

The accuracy for target tracking using a conventional interacting multiple-model algorithm (IMM) is limited. In this paper, a new variable structure of interacting multiple-model (VSIMM) algorithm aided by center scaling (VSIMM-CS) is proposed to solve this problem. The novel VSIMM-CS has two main steps. Firstly, we estimate the approximate location of the true model. This is aided by the expected-mode augmentation algorithm (EMA), and a new method—namely, the expected model optimization method—is proposed to further enhance the accuracy of EMA. Secondly, we change the original model set to ensure the current true model as the symmetry center of the current model set, and the model set is scaled down by a certain percentage. Considering the symmetry and linearity of the system, the errors produced by symmetrical models can be well offset. Furthermore, narrowing the distance between the true model and the default model is another effective method to reduce the error. The second step is based on two theories: symmetric model set optimization method and proportional reduction optimization method. All proposed theories aim to minimize errors as much as possible, and simulation results highlight the correctness and effectiveness of the proposed methods.

Abstract A critical challenge lies in developing an energy-efficient and eco-friendly power supply system. Despite the enhanced energy efficiency offered by combined cooling, heating, and power (CCHP) systems, optimizing them poses challenges due to conflicting goals like reducing fuel consumption and carbon dioxide emissions while maximizing cost savings. To address these issues, this research suggests a solution that merges a modified subtraction-average-based optimizer with a multiobjective optimization strategy. This proposed framework attains a superior equilibrium among competing objectives compared to three existing optimization algorithms. It leads to a 12% decrease in fuel consumption, a 15% drop in carbon dioxide emissions, and a 10% cost reduction for shopping center proprietors. Moreover, the optimized CCHP system outperforms a stand-alone production system and a nonoptimized CCHP system, yielding 20% and 15% fuel savings annually, respectively. By offering a more comprehensive and balanced approach to CCHP system optimization, the proposed framework contributes to the progression of energy system optimizer, fostering the creation of more sustainable and environmentally friendly energy systems of shopping centers.

Inverse problems for a 3D model of electrostatics, which arise when developing technologies for designing electric cloaking and shielding devices, are studied. It is assumed that the devices being designed to consist of a finite number of concentric spherical layers filled with homogeneous anisotropic or isotropic media. A mathematical technique for solving these problems has been developed. It is based on the formulation of cloaking or shielding problems in the form of inverse problems for the electrostatic model under consideration, reducing the latter problems to finite-dimensional extremum problems, and finding their solutions using one of the global minimization methods. Using the developed technology, the inverse problems are replaced by control problems, in which the role of controls is played by the permittivities of separate layers composing the device being designed. To solve them, a numerical algorithm based on the particle swarm optimization method is proposed. Important properties of optimal solutions are established, one of which is the bang-bang property. It is shown on the base of the computational experiments that cloaking and shielding devices designed using the developed algorithm have the simplicity of technical implementation and the highest performance in the class of devices under consideration.

The development of the promising Artificial Intelligence of The things (AIoT) technology increases the demand for implementing Convolutional Neural Networks (CNN) algorithms on the edge devices. However, implementing huge CNN-based applications on the resource-constrained edge devices is considered challenging. Therefore, several CNN optimization methods are integrated into the deployment tools of the edge devices. Since this field evolves rapidly, relevant tools adopt non-uniform deployment optimization flows, and the optimization details are poorly explained. This fact hinders developers from further analyzing the bottlenecks of the CNN-based applications on the edge devices. Hence, the paper comprehensively analyzes the deployment optimization methods for the CNN-based applications on the edge devices. Optimization methods are classified into the Hardware-Agnostic and Hardware-Specific methods. Their ideas and processing details are analyzed, and some suggestions are proposed according to the deployment experiments with different architecture models.

Soil carbon is becoming increasingly difficult to predict due to uncertainties in climate warming. The main objective of this research is to estimate the scope of uncertainties in soil carbon, which is the difference between maximal and minimal estimations of soil carbon, caused by uncertainties in climate change in China, by applying the Lund–Potsdam–Jena (LPJ) model and an improved optimization method. Based on an original optimization method (conditional nonlinear optimal parameter perturbation, CNOP‐P), a cost function is revised to evaluate the scope of uncertainties in predicting soil carbon sequestration, avoiding the overestimation of uncertainties. Two types of climate change projections are obtained from 10 global circulation models (GCMs) under the Representative Concentration Pathway (RCP) 4.5 scenario using two methods. For the first type of climate change projection, the upper and lower limits of estimated future soil carbon sequestration are 102.7 and 65.5 Gt, respectively, whereas the reference soil carbon sequestration driven by an ensemble of 10 GCMs is 79.6 Gt. The estimated future soil carbon sequestration ranges from 79.4 to 91.6 Gt for the second type of climate change. The numerical results imply that these two types of climate change, constrained by the projection of 10 GCMs, are the main factors affecting the uncertainty range of estimated soil carbon. The spatial distributions of average soil carbon stocks driven by the CNOP‐P‐Variance‐type and CNOP‐P‐Min‐Max‐type climate change scenarios and outputs from 10 GCMs. (a) Reference state; (b) CNOP‐Min‐Max‐Lower‐type climate change scenario; (c) CNOP‐Min‐Max‐Upper‐type climate change scenario; (d) CNOP‐Variance‐Lower‐type climate change scenario; and (e) CNOP‐Variance ‐Upper‐type climate change scenario. (Unit: kg C m−2 year−1). CNOP‐P, conditional non‐linear optimal parameter perturbation; GCMs, general climate models.

To overcome the deficiencies of weak local search ability in genetic algorithms (GA) and slow global convergence speed in ant colony optimization (ACO) algorithm in solving complex optimization problems, the chaotic optimization method, multi-population collaborative strategy and adaptive control parameters are introduced into the GA and ACO algorithm to propose a genetic and ant colony adaptive collaborative optimization (MGACACO) algorithm for solving complex optimization problems. The proposed MGACACO algorithm makes use of the exploration capability of GA and stochastic capability of ACO algorithm. In the proposed MGACACO algorithm, the multi-population strategy is used to realize the information exchange and cooperation among the various populations. The chaotic optimization method is used to overcome long search time, avoid falling into the local extremum and improve the search accuracy. The adaptive control parameters is used to make relatively uniform pheromone distribution, effectively solve the contradiction between expanding search and finding optimal solution. The collaborative strategy is used to dynamically balance the global ability and local search ability, and improve the convergence speed. Finally, various scale TSP are selected to verify the effectiveness of the proposed MGACACO algorithm. The experiment results show that the proposed MGACACO algorithm can avoid falling into the local extremum, and takes on better search precision and faster convergence speed.

To improve the crashworthiness of vehicles, the crashworthiness of the vehicle structure itself has to be optimised. Through the collision analysis of a certain high-speed train, this research found that the front-end structure is most important in the crashworthiness optimisation design of the vehicle; the constitutive material models required for this numerical simulation of an entire vehicle were obtained by performing loading tests at different strain rates; according to the highly non-linear characteristics of the ensuing structural deformation under impact loading, this research used specific energy absorption (SEA) as an objective function to construct a multi-parameter optimisation model of the front-end structure of the vehicle . Based on this, the optimisation analysis was conducted. In the optimisation, the optimal SEA value (3.6988 kJ/kg) of the structure is obtained by 130-step iteration using a modified method of feasible directions (MMFD)—a gradient optimisation method; the optimal value obtained after 101 iterations by applying a direct search method—Hooke-Jeeves (HJ) algorithm is 3.6454 kJ/kg; and the optimal value acquired after 192 iterations of a global optimisation method—adaptive simulated annealing (ASA)—is 3.6132 kJ/kg. Moreover, the optimum results were validated by collision analysis of the optimal structure using a MMFD model. The variation analysis of the structural SEA with each variable show that the optimisation model is able to extend the range of each design variable.